Recent Advances in Voice Generation, Cloning and Sound Generation with AI

Professor Wu, creator for the Siri Cantonese voice at Apple, currently runs several Inno-labs at the Chinese University of Hong Kong (SZ). With past experience at Meta (Facebook), Microsoft Research, and the University of Edinburgh, he brings a wealth of expertise in sound technology. In this talk, Prof. Wu explores speech synthesis, voice cloning, sound making, and their transformative potential with AI. He will share his latest research and reveal how these innovations can revolutionise music education, sound engineering, inspiring APA teachers and students to explore new artistic possibilities through AI.